taskai

A command-line task manager with AI features.

pip install taskai-cli

Setup

task setup

Commands

task                              interactive mode

task show all                     show everything
task show <id|name>               show a specific item
task show <id1>,<id2>,...         show multiple items

task create <name>                create a top-level item
task add <parent> <name>          add a child item
task update <id> --field value    update any field
task rename <id> <new name>       rename an item
task move <item> <new parent>     reparent an item
task complete <id>                mark complete (recursive)
task delete <id|name>             delete by id or name
task delete completed             delete all completed items
task clear <parent>               delete completed under a parent

task comment <id> <text>          add a comment
task depend <src_id> <dst_id>     src depends on dst
task link <parent> <item>         soft-link two items
task reorder <id1> before|after <id2>

task status <id> <text>           set a status string
task pomo <on_mins> <off_mins>    pomodoro timer

task ai <prompt>                  natural language → commands
task ai headstart <id>            AI suggests next step, saved as comment

task config show                  list current config
task config set <key> <value>     set a config value
task config get <key>             get a config value
task config pop <key>             remove a config value

task repair                       repair the database
task nuke                         delete all data

Item fields

Pass any of these as --field value to create, add, or update:

Field	Format	Example
`description`	string	`--description "needs review"`
`due_by`	MM-DD-YYYY	`--due_by 08-15-2026`
`priority`	integer	`--priority 2`
`status`	string	`--status "in progress"`
`completed`	bool	`--completed true`
`depends_on`	comma-separated ids	`--depends_on 3,7`

Config

AI features require a model, set as a provider/model string (via litellm), plus that provider's credentials set as environment variables (e.g. GEMINI_API_KEY, OPENAI_API_KEY). task setup will walk you through picking a provider and model and tell you which env vars it needs.

task config set AI_MODEL gemini/gemini-2.0-flash

Example

task create "Today"
task add "Today" "Morning run"
task add "Today" "Review pull requests" --status "blocked"
task add "Today" "Call dentist" --due_by 08-02-2026
task show "Today"
task complete 4
task show "Today"
task exit

Or:

task ai "add a task called 'Reply to Alex' under Today, and mark the dentist task as done"

Another Example

task create "Launch website"

# add subtasks (by name or id)
task add "Launch website" "Write copy"
task add "Launch website" "Design mockups" --priority 1
task add "Launch website" "Set up hosting" --due_by 08-15-2026

# check your work
task show "Launch website"

# ask AI what to do first on a specific task
task ai headstart 3

# mark something done and clean up
task complete 2
task clear "Launch website"

Release files for taskai-cli 1.6.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for taskai-cli 1.6.2
File	Size	Uploaded
taskai_cli-1.6.2.tar.gz	54.1 kB	Aug 24, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for taskai-cli 1.6.2
File	Interpreter	ABI	Platform	Reset
taskai_cli-1.6.2-py3-none-any.whl 34.4 kB Aug 24, 2026	Python 3	none	any	Details

Total release size: 88.5 kB

Release files / taskai_cli-1.6.2.tar.gz

Download URL	taskai_cli-1.6.2.tar.gz
Size	54.1 kB
Tags	Source
SHA-256 checksum How to use checksums	`d1f4baae6775877707a53a46d98eff65d0626acc28893e0b71c1caf05514ebcd`
BLAKE2b-256 checksum How to use checksums	`0047d2164576cf7149c95a601b89a95d5d87c8844cb3acfcbce00bf9d1dd933e`
Upload date	Aug 24, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/alexander-paskal/taskai
Publishing commit: github.com/alexander-paskal/taskai/tree/d5ad4312ebe49ee4d4d2628f6110279a7f6711df

Workflow

Publishing configuration: github.com/alexander-paskal/taskai/blob/d5ad4312ebe49ee4d4d2628f6110279a7f6711df/.github/workflows/publish-to-pypi.yml
Publishing logs: github.com/alexander-paskal/taskai/actions/runs/32759546362/attempts/1

Artifact

Subject: taskai_cli-1.6.2.tar.gz
SHA-256 checksum: d1f4baae6775877707a53a46d98eff65d0626acc28893e0b71c1caf05514ebcd Verifying attestations

Release files / taskai_cli-1.6.2-py3-none-any.whl

Download URL	taskai_cli-1.6.2-py3-none-any.whl
Size	34.4 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`59cdae7f0182e9fbfca1c773ad6484c967f2370ce3d3c06ba814c7c2fad47b19`
BLAKE2b-256 checksum How to use checksums	`97e5254c6b73f3b130b2fdbac79b562f24f0e2581d19a6976d29aae85a3599fc`
Upload date	Aug 24, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/alexander-paskal/taskai
Publishing commit: github.com/alexander-paskal/taskai/tree/d5ad4312ebe49ee4d4d2628f6110279a7f6711df

Workflow

Publishing configuration: github.com/alexander-paskal/taskai/blob/d5ad4312ebe49ee4d4d2628f6110279a7f6711df/.github/workflows/publish-to-pypi.yml
Publishing logs: github.com/alexander-paskal/taskai/actions/runs/32759546362/attempts/1

Artifact

Subject: taskai_cli-1.6.2-py3-none-any.whl
SHA-256 checksum: 59cdae7f0182e9fbfca1c773ad6484c967f2370ce3d3c06ba814c7c2fad47b19 Verifying attestations